.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/codegraphtheory/heavy-coder
home/skills/codegraphtheory/heavy-coder
codegraphtheory avatar

codegraphtheory/heavy-coder

15 skills

View on GitHub
$npx skills add codegraphtheory/heavy-coder
SkillInstalls
heavy-coding-evalDesign and scaffold evaluations comparing single-candidate Composer coding against adaptive Heavy Coder candidate teams.—heavy-context-budgetKeep coordinator and leaf context lean-batch reads, cap logs, use execute_code to filter-so swarms stay fast and within token limits.—heavy-explore-firstUse at the start of non-trivial software tasks. Gather repo ground truth with batched reads and searches before planning or delegate_task.—heavy-hook-phasesObey Plan 1A hook session phases so mutating tools, delegate_task sizing, and re-planning do not waste turns or trigger blocks.—heavy-issue-to-mergeCoordinate Heavy Coder issue-to-PR and future fail-closed issue-to-merge workflows. Current phase provides contracts, dry-run scripts, and safety gates only.—heavy-leaf-briefUse when spawning delegate_task leaves for coding work. Pack self-contained goals and context so parallel Composer workers ship verifiable patches without…—heavy-leaf-candidate-outputRequire structured candidate-result JSON from swarm leaves so critique_candidates.py and synthesis run on evidence, not prose self-reports.—heavy-pre-dispatch-enrichEnrich slim hook-injected delegate_tasks with touch map, failure excerpts, and verification commands so parallel leaves produce verifiable patches without…—heavy-repair-waveAfter failed candidates or a red ship gate, spawn a narrow focused delegate_task wave with failure evidence instead of re-running a full-width council.—heavy-scope-routerRoute every user request to read-only exploration, single-agent work, full Composer swarm, or GitHub issue flow before spending tokens or spawning leaves.—heavy-ship-gateUse before telling the user a coding task is done or opening a PR.—heavy-single-modeHonor explicit single-agent opt-out from council hooks-solo coordinator implementation with the same evidence bar as swarm mode.—heavy-swarm-dispatchAfter team plan injection, dispatch one full-width delegate_task batch immediately, notify the user how to watch the swarm, and avoid wasted coordinator turns…—heavy-synthesize-winnerUse after delegate_task leaves finish. Blind-compare candidate evidence, merge one coherent implementation, and avoid Frankenstein patches before verification.—heavy-team-defaultDefault Composer swarm workflow for Heavy Coder (route, enrich, dispatch, critique, synthesis, verification).—